sam2.1-hiera-small
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve facebook/sam2.1-hiera-smallNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
sam2.1-hiera-small is an open-weight image segmentation model published by facebook on Hugging Face in September 2024, with 50M parameters under the apache-2.0 license.
Among the 23 image segmentation models in this directory it ranks 11th by monthly Hugging Face downloads, and 18 of the others are larger.
HardwareLink to this section
Unquantized FP16 weights take about 1 GB; 8-bit brings that to ~1 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. At this size it runs on almost any recent GPU, on Apple Silicon, and usable on a modern CPU. Check exact numbers for your card with the VRAM calculator.
Similar image segmentation modelsLink to this section
- segformer_b2_clothes - 30M, 336,301 downloads/month
- RMBG-1.4 - 40M, 229,106 downloads/month
- sam2.1-hiera-tiny - 40M, 163,502 downloads/month
- face-parsing - 80M, 145,329 downloads/month
- fashn-human-parser - 60M, 76,198 downloads/month
PopularityLink to this section
sam2.1-hiera-small was downloaded 168,596 times on Hugging Face in the last month (599,605 all-time) and has 27 likes.
Run it locallyLink to this section
Weights and usage instructions are on the facebook/sam2.1-hiera-small model card; it loads with Hugging Face Transformers.
Local runtimes that fit this model:
- comfyui - node-based workflows, the usual way to run diffusion models locally
- invokeai - a canvas UI for image generation and editing
- transformers - the reference Python library most model cards target
PaperLink to this section
Frequently asked
Quick answers to common questions
How much VRAM does sam2.1-hiera-small need?
sam2.1-hiera-small with 50M parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is sam2.1-hiera-small better than other facebook models?
sam2.1-hiera-small has 50M parameters - a strong choice for image-segmentation.
What license is sam2.1-hiera-small under?
sam2.1-hiera-small is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs sam2.1-hiera-small well?
With 50M parameters, sam2.1-hiera-small is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs. Check our hardware directory for specific recommendations.
What is the best quantization for sam2.1-hiera-small?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with sam2.1-hiera-small?
sam2.1-hiera-small competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec